Search

Your search keyword '"Taghiyarrenani, Zahra"' showing total 17 results
Start Over Author "Taghiyarrenani, Zahra"
17 results on '"Taghiyarrenani, Zahra"'

1. Heterogeneous Federated Learning via Personalized Generative Networks

Author

Taghiyarrenani, Zahra, Alabdallah, Abdallah, Nowaczyk, Slawomir, and Pashami, Sepideh

Subjects
Computer Science - Machine Learning
Abstract

Federated Learning (FL) allows several clients to construct a common global machine-learning model without having to share their data. FL, however, faces the challenge of statistical heterogeneity between the client's data, which degrades performance and slows down the convergence toward the global model. In this paper, we provide theoretical proof that minimizing heterogeneity between clients facilitates the convergence of a global model for every single client. This becomes particularly important under empirical concept shifts among clients, rather than merely considering imbalanced classes, which have been studied until now. Therefore, we propose a method for knowledge transfer between clients where the server trains client-specific generators. Each generator generates samples for the corresponding client to remove the conflict with other clients' models. Experiments conducted on synthetic and real data, along with a theoretical study, support the effectiveness of our method in constructing a well-generalizable global model by reducing the conflict between local models.

Published
2023

2. Towards Explainable Deep Domain Adaptation

Author

Bobek, Szymon, Nowaczyk, Sławomir, Pashami, Sepideh, Taghiyarrenani, Zahra, Nalepa, Grzegorz J., Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Nowaczyk, Sławomir, editor, Biecek, Przemysław, editor, Chung, Neo Christopher, editor, Vallati, Mauro, editor, Skruch, Paweł, editor, Jaworek-Korjakowska, Joanna, editor, Parkinson, Simon, editor, Nikitas, Alexandros, editor, Atzmüller, Martin, editor, Kliegr, Tomáš, editor, Schmid, Ute, editor, Bobek, Szymon, editor, Lavrac, Nada, editor, Peeters, Marieke, editor, van Dierendonck, Roland, editor, Robben, Saskia, editor, Mercier-Laurent, Eunika, editor, Kayakutlu, Gülgün, editor, Owoc, Mieczyslaw Lech, editor, Mason, Karl, editor, Wahid, Abdul, editor, Bruno, Pierangela, editor, Calimeri, Francesco, editor, Cauteruccio, Francesco, editor, Terracina, Giorgio, editor, Wolter, Diedrich, editor, Leidner, Jochen L., editor, Kohlhase, Michael, editor, and Dimitrova, Vania, editor

Published
2024
Full Text
View/download PDF

3. Data-Centric Perspective on Explainability Versus Performance Trade-Off

Author

Berenji, Amirhossein, Nowaczyk, Sławomir, Taghiyarrenani, Zahra, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Crémilleux, Bruno, editor, Hess, Sibylle, editor, and Nijssen, Siegfried, editor

Published
2023
Full Text
View/download PDF

4. curr2vib: Modality Embedding Translation for Broken-Rotor Bar Detection

Author

Berenji, Amirhossein, Taghiyarrenani, Zahra, Nowaczyk, Sławomir, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Koprinska, Irena, editor, Mignone, Paolo, editor, Guidotti, Riccardo, editor, Jaroszewicz, Szymon, editor, Fröning, Holger, editor, Gullo, Francesco, editor, Ferreira, Pedro M., editor, Roqueiro, Damian, editor, Ceddia, Gaia, editor, Nowaczyk, Slawomir, editor, Gama, João, editor, Ribeiro, Rita, editor, Gavaldà, Ricard, editor, Masciari, Elio, editor, Ras, Zbigniew, editor, Ritacco, Ettore, editor, Naretto, Francesca, editor, Theissler, Andreas, editor, Biecek, Przemyslaw, editor, Verbeke, Wouter, editor, Schiele, Gregor, editor, Pernkopf, Franz, editor, Blott, Michaela, editor, Bordino, Ilaria, editor, Danesi, Ivan Luciano, editor, Ponti, Giovanni, editor, Severini, Lorenzo, editor, Appice, Annalisa, editor, Andresini, Giuseppina, editor, Medeiros, Ibéria, editor, Graça, Guilherme, editor, Cooper, Lee, editor, Ghazaleh, Naghmeh, editor, Richiardi, Jonas, editor, Saldana, Diego, editor, Sechidis, Konstantinos, editor, Canakoglu, Arif, editor, Pido, Sara, editor, Pinoli, Pietro, editor, Bifet, Albert, editor, and Pashami, Sepideh, editor

Published
2023
Full Text
View/download PDF

5. Towards Geometry-Preserving Domain Adaptation for Fault Identification

Author

Taghiyarrenani, Zahra, Nowaczyk, Sławomir, Pashami, Sepideh, Bouguelia, Mohamed-Rafik, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Koprinska, Irena, editor, Mignone, Paolo, editor, Guidotti, Riccardo, editor, Jaroszewicz, Szymon, editor, Fröning, Holger, editor, Gullo, Francesco, editor, Ferreira, Pedro M., editor, Roqueiro, Damian, editor, Ceddia, Gaia, editor, Nowaczyk, Slawomir, editor, Gama, João, editor, Ribeiro, Rita, editor, Gavaldà, Ricard, editor, Masciari, Elio, editor, Ras, Zbigniew, editor, Ritacco, Ettore, editor, Naretto, Francesca, editor, Theissler, Andreas, editor, Biecek, Przemyslaw, editor, Verbeke, Wouter, editor, Schiele, Gregor, editor, Pernkopf, Franz, editor, Blott, Michaela, editor, Bordino, Ilaria, editor, Danesi, Ivan Luciano, editor, Ponti, Giovanni, editor, Severini, Lorenzo, editor, Appice, Annalisa, editor, Andresini, Giuseppina, editor, Medeiros, Ibéria, editor, Graça, Guilherme, editor, Cooper, Lee, editor, Ghazaleh, Naghmeh, editor, Richiardi, Jonas, editor, Saldana, Diego, editor, Sechidis, Konstantinos, editor, Canakoglu, Arif, editor, Pido, Sara, editor, Pinoli, Pietro, editor, Bifet, Albert, editor, and Pashami, Sepideh, editor

Published
2023
Full Text
View/download PDF

6. Domain Adaptation with Maximum Margin Criterion with Application to Network Traffic Classification

Author

Taghiyarrenani, Zahra, Farsi, Hamed, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Koprinska, Irena, editor, Mignone, Paolo, editor, Guidotti, Riccardo, editor, Jaroszewicz, Szymon, editor, Fröning, Holger, editor, Gullo, Francesco, editor, Ferreira, Pedro M., editor, Roqueiro, Damian, editor, Ceddia, Gaia, editor, Nowaczyk, Slawomir, editor, Gama, João, editor, Ribeiro, Rita, editor, Gavaldà, Ricard, editor, Masciari, Elio, editor, Ras, Zbigniew, editor, Ritacco, Ettore, editor, Naretto, Francesca, editor, Theissler, Andreas, editor, Biecek, Przemyslaw, editor, Verbeke, Wouter, editor, Schiele, Gregor, editor, Pernkopf, Franz, editor, Blott, Michaela, editor, Bordino, Ilaria, editor, Danesi, Ivan Luciano, editor, Ponti, Giovanni, editor, Severini, Lorenzo, editor, Appice, Annalisa, editor, Andresini, Giuseppina, editor, Medeiros, Ibéria, editor, Graça, Guilherme, editor, Cooper, Lee, editor, Ghazaleh, Naghmeh, editor, Richiardi, Jonas, editor, Saldana, Diego, editor, Sechidis, Konstantinos, editor, Canakoglu, Arif, editor, Pido, Sara, editor, Pinoli, Pietro, editor, Bifet, Albert, editor, and Pashami, Sepideh, editor

Published
2023
Full Text
View/download PDF

10. Fault identification with limited labeled data.

Author

Berenji, Amirhossein, Taghiyarrenani, Zahra, and Rohani Bastami, Abbas

Subjects
*DEEP learning, *FAULT diagnosis, *ROLLER bearings
Abstract

Intelligent fault diagnosis (IFD) based on deep learning methods has shown excellent performance, however, the fact that their implementation requires massive amount of data and lack of sufficient labeled data, limits their real-world application. In this paper, we propose a two-step technique to extract fault discriminative features using unlabeled and a limited number of labeled samples for classification. To this end, we first train an Autoencoder (AE) using unlabeled samples to extract a set of potentially useful features for classification purpose and consecutively, a Contrastive Learning-based post-training is applied to make use of limited available labeled samples to improve the feature set discriminability. Our Experiments—on SEU bearing dataset—show that unsupervised feature learning using AEs improves classification performance. In addition, we demonstrate the effectiveness of the employment of contrastive learning to perform the post-training process; this strategy outperforms Cross-Entropy based post-training in limited labeled information cases. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results